计算机科学 ›› 2018, Vol. 45 ›› Issue (2): 98-102.doi: 10.11896/j.issn.1002-137X.2018.02.017

• 2017年中国计算机学会人工智能会议 • 上一篇    下一篇

一种动态调整惯性权重的粒子群优化算法

董红斌,李冬锦,张小平   

  1. 哈尔滨工程大学计算机科学与技术学院 哈尔滨150001,哈尔滨工程大学计算机科学与技术学院 哈尔滨150001,中国中医科学院 北京100700
  • 出版日期:2018-02-15 发布日期:2018-11-13
  • 基金资助:
    本文受国家自然科学基金项目(61472095,6)资助

Particle Swarm Optimization Algorithm with Dynamically Adjusting Inertia Weight

DONG Hong-bin, LI Dong-jin and ZHANG Xiao-ping   

  • Online:2018-02-15 Published:2018-11-13

摘要: 针对粒子收敛速度慢、搜索精度不高和算法性能在很大程度上依赖于参数的选取等缺点,提出了一种非线性指数惯性权重粒子群优化算法(Exponential Inertia Weight in Particle Swarm Optimization,EIW-PSO)。在每次迭代的过程中, 采用粒子最大适应值和最小适应值的指数函数来动态调整 算法中的惯性权重,更有利于算法在寻优过程中跳出局部最优;同时,引入随机因子以确保种群的多样性,使粒子更快地收敛到全局最优位置。为了验证该算法的寻优性能,通过8个基准测试函数将标准PSO、线性递减惯性权重LDIW-PSO、均值自适应惯性权重MAW-PSO在不同维度和种群规模下进行测试比较。实验结果表明,提出的EIW-PSO算法具有更快的收敛速度和更高的求解精度。

关键词: 粒子群优化算法,动态调整,惯性权重,指数函数

Abstract: In order to tackle the problems of slow convergence,low accuracy and parameter dependence of the standard particle swarm optimization(PSO) algorithm,a nonlinear exponential inertia weight in particle swarm optimization(EIW-PSO) was proposed.In each iteration,the new algorithm improves its performance by adjusting inertia weight dynamically.The new weight is an exponential function of the minimal and maximal fitness of the particles,which is more conducive for the algorithm being out of local optimization in optimization process. Random factors are introduced to ensure population diversity,so that the particles converge to the global optimal position faster.The standard PSO,linearly decreasing inertia weigh (LDIW-PSO),mean adaptive inertia weigh (MAW-PSO) were tested and compared in different dimensions and population sizes through eight benchmark test functions.Experimental results show that the proposed EIW-PSO algorithm has faster convergence rate and higher solving precision.

Key words: Particle swarm optimization algorithm,Dynamically adjusting,Inertia weight,Exponential function

[1] KENNEDY J,EBERHERT R.Particle Swarm Optimization[C]∥IEEE International Conference on Neural Networks.Australia:IEEE,1995:1942-1948.
[2] ELEGBEDE C.Structural Reliability Assessment based on Particles Swarm Optimization [J].Structural Safety,2005,7(10):171-186.
[3] POBINSON J,RAHMAT Y.Particle Swarm Optimization inElectrom Agnetics [J].IEEE Transactions on Antennas and Propagation,2004,2(2):397-406.
[4] SALMAN A,AHMAD I,MADANI S.Particle Swarm Optimization for Task Assignment Problem [J].Microprocessors and Microsystems,2002,6(8):363-371.
[5] SHI Y,EBERHART R.Empirical Study of Particle Swarm Optimization[C]∥International Conference on Evolutiona-ry Compution.Washington,USA:IEEE,1999:1945-1950.
[6] SHI Y,EBERHART R.Fuzzy Adaptive Particle Swarm Optimization[J].Congress on Evolutionary Compution,2001,1(12):101-106.
[7] EBERHART R,SHI Y.Tracking and Optimizing Dynamic Systems with Particle Swarm[J].Congress on Evolutionary Computatiion,2001,1(1):94-100.
[8] ZHAO Z G,LIN Y J,YIN Z Y.A Mean Particle Swarm Optimization Algorithm based on Adaptive Inertia Weight [J].Journal of Computer Engineering & Science,2016,8(3):501-506.(in Chinese) 赵志刚,林玉娇,尹兆远.基于自适应惯性权重的均值粒子群优化算法[J].计算机工程与科学,2016,38(3):501-506.
[9] CHALEM S,ONGSAKUL W.Stochastic Weight Tradeoff Particle Swarm Optimization for Nonconvex Economic Dispatch [J].Energy Conversion and Management,2013,0:66-75.
[10] XIA X W,LIU J N,HU Z B.An Improved Particle Swarm Optimizer based on Tabu Detecting and Local Learning Strategy in a Shrunk Search Space [J].Applied Soft Computing,2014,3(1):76-90.
[11] PARSOPOULOS K E.Parallel Cooperative Micro-Particle SwarmOptimization:A Master-slave Model [J].Applied Soft Computing,2012,2(11):3552-3579.
[12] ALFI A.PSO with Adaptive Mutation and Inertia Weight and its Application in Parameter Estimation of Dynamic Systems [J].Acta Automatica Sinica,2011,7(5):541-549.
[13] ZHANG Y,GONG D W.Feature Selection Algorithm based on Bare Bones Particle Swarm Optimization [J].Neurocomputing,2015,8(1):150-157.
[14] ZHANG Y,GONG D W,SUN X Y.Adaptive Bare Bones Particle Swarm Optimization Algorithm and its Convergence Analysis [J].Soft Computing,2014,8(7):1337-1352.
[15] TENG X Y,DONG H B,SUN J.Co-evolution Algorithm forFeature Selection [J].Journal of CAAI Transactions on Intelligent Systems,2017,2(1):1-9.(in Chinese) 滕旭阳,董红斌,孙静.面向特征选择问题的协同演化方法[J].智能系统学报,2017,12(1):1-9.
[16] DONG H B,YANG X,TENG X Y.A Diversity Reserved Quantum Particle Swarm Optimization Algorithm for MMKP[C]∥ IEEE/ACIS Internation Conference on Computer and Information Science (ICIS).2016:1-7.
[17] LI X J,XU J,ZHU E Z.A Novel Computation Method for Adaptive Inertia Weight of Task Scheduling Algorithm [J].Journal of Computer Research and Development,2016,3(9):1990-1999.(in Chinese) 李学俊,徐佳,朱二周.任务调度算法中新的自适应惯性权重计算法[J].计算机研究与发展,2016,3(9):1990-1999.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!